Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to friendships and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "friends" or "friend."

    np_acts-logits-general · gemini-2.0-flash

    friends / friend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.52
    JsonInclude
    -0.51
     AssemblyVersion
    -0.49
    ỏa
    -0.49
    Quais
    -0.49
    }")]
    -0.48
    Vey
    -0.48
     
    -0.47
    }>;
    -0.47
    ])):
    -0.47
    POSITIVE LOGITS
     friends
    1.09
    friend
    1.05
     friend
    1.05
    Friend
    1.03
     Friend
    1.02
     Friends
    1.01
     FRIEND
    0.99
    Friends
    0.98
    friends
    0.94
    FRIEND
    0.94
    Act Density 0.043%

    No Known Activations